BROWSE
Detail
Journal Article
HeteroAccel: 엣지 컴퓨팅 환경에서의 다양한 영상 추론을 위한 쿠버네티스 기반의 이종 연산·가속기 자원 관리 시스템
Cited - time in 
Share 
Share
- Issue Date
- 2021-10
- Citation
- 대한임베디드공학회논문지, v.16, no.5, pp.201-207
- ISSN
- 1975-5066
- Publisher
- 대한임베디드공학회
- Language
- Korean
- Type
- Journal Article
- Abstract
- Edge Computing enables image-based inference in close proximity to end users and real-world objects. However, since edge servers have limited computational and accelerator resources, efficient resource management is essential. In this paper, we present HeteroAccel system that performs optimal scheduling in Kubernetes platform based on available node and accelerator information for various inference requests. Our experiments showed 25.3% improvement in overall inference performance over the default scheduling scheme in edge computing environment in which four types of inference services are requested.
- KSP Keywords
- Computing Environment, Edge Computing, End users, Image-based, Optimal scheduling, Real-world objects, Resource management, Scheduling Scheme, close proximity